Accelerating the design of compositionally complex materials via physics-informed artificial intelligence

Raabe, Dierk; Mianroodi, Jaber Rezaei; Neugebauer, Jörg

doi:10.1038/s43588-023-00412-7

Cited by 34 publications

(20 citation statements)

References 165 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Based on our understanding, four research directions using SECCM are proposed as follows: (1) studies on the relationship between specific microstructures and the electrochemical properties of metallic materials; (2) exploring the relationship between microelectrochemical properties and macroscopic corrosion behavior; (3) processing and analysis of microelectrochemical big data; (4) digitalization research of the corrosion of metallic materials. With great prospects, we should employ data mining tools reasonably to maximize the potential of big data acquired from SECCM, thus promoting corrosion research from experimental and computational simulation to a data-driven direction for future study.…”

Section: ■ Conclusionmentioning

confidence: 99%

“…Additionally, there are various heterogeneous microstructures present both on the metallic surfaces and within the bulk, including intermetallics, inclusions, grains, phase boundaries, and other defects. 1 It is essential to understand these factors since heterogeneity adds complexity to the corrosion behavior of metals and alloys. Thus, effective strategies for corrosion protection can be proposed by understanding the underlying mechanisms.…”

Section: ■ Introductionmentioning

confidence: 99%

“…Metallic materials utilized in the industrial field are usually polycrystalline, containing various crystallographic orientations and grain sizes. Additionally, there are various heterogeneous microstructures present both on the metallic surfaces and within the bulk, including intermetallics, inclusions, grains, phase boundaries, and other defects . It is essential to understand these factors since heterogeneity adds complexity to the corrosion behavior of metals and alloys.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Perspectives on Corrosion Studies Using Scanning Electrochemical Cell Microscopy: Challenges and Opportunities

Lai,

Liu,

et al. 2023

Anal. Chem.

View full text Add to dashboard Cite

Scanning electrochemical cell microscopy (SECCM) allows for electrochemical imaging at the micro-or nanoscale by confining the electrochemical reaction cell in a small meniscus formed at the end of a micro-or nanopipette. This technique has gained popularity in electrochemical imaging due to its high-throughput nature. Although it shows considerable application potential in corrosion science, there are still formidable and exciting challenges to be faced, particularly relating to the high-throughput characterization and analysis of microelectrochemical big data. The objective of this perspective is to arouse attention and provide opinions on the challenges, recent progress, and future prospects of the SECCM technique to the electrochemical society, particularly from the viewpoint of corrosion scientists. Specifically, four main topics are systematically reviewed and discussed: (1) the development of SECCM; (2) the applications of SECCM for corrosion studies; (3) the challenges of SECCM in corrosion studies; and (4) the opportunities of SECCM for corrosion science.

show abstract

Section: ■ Conclusionmentioning

confidence: 99%

Section: ■ Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Perspectives on Corrosion Studies Using Scanning Electrochemical Cell Microscopy: Challenges and Opportunities

Lai,

Liu,

et al. 2023

Anal. Chem.

View full text Add to dashboard Cite

show abstract

“…As a powerful tool to address the above challenges, PIML [17,18], which embeds physical information into ML to guide its training, has received increasing attention in science and industry. Although the theoretical system of PIML has just been established, considering the great potential and broad research prospects it shows, PIML has been thoroughly explored in many fields, including power systems [19], heat transfer [20], fluid mechanics [21] and so on [22][23][24][25][26][27]. Owing to varying degrees of simplification, physically based models make it difficult to model complex failure processes in structural integrity, and the performance of purely data-driven ML are limited by sparse data.…”

Section: Introductionmentioning

confidence: 99%

Physics-informed machine learning and its structural integrity applications: state of the art

Zhu,

Wang,

Luo

et al. 2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

The development of machine learning (ML) provides a promising solution to guarantee the structural integrity of critical components during service period. However, considering the lack of respect for the underlying physical laws, the data hungry nature and poor extrapolation performance, the further application of pure data-driven methods in structural integrity is challenged. An emerging ML paradigm, physics-informed machine learning (PIML), attempts to overcome these limitations by embedding physical information into ML models. This paper discusses different ways of embedding physical information into ML and reviews the developments of PIML in structural integrity including failure mechanism modelling and prognostic and health management (PHM). The exploration of the application of PIML to structural integrity demonstrates the potential of PIML for improving consistency with prior knowledge, extrapolation performance, prediction accuracy, interpretability and computational efficiency and reducing dependence on training data. The analysis and findings of this work outline the limitations at this stage and provide some potential research direction of PIML to develop advanced PIML for ensuring structural integrity of engineering systems/facilities. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 1)'.

show abstract

“…Dabei werden kristal line Festkörper mit zum Teil äquimolaren, also gleich großen, Anteilen aus bis zu sieben metallischen Elementen zusammengemischt. Unterstützt durch die entsprechende Konfigurationsentropie kommt es dabei in einigen Fällen zu homogen festen Lösungen, bei anderen hingegen zu Entmischung und atomaren Ordnungsbildung, also zu loka len atomaren Gitterbereichen mit Überstruktur [1]. Das Konzept dieser HochentropieLegierungen wird jüngst auch auf andere Materialklassen wie etwa Keramiken, Poly mere, Halbleiter oder niedrigdimensionale Werkstoffe über tragen [2,3].…”

unclassified

Metalle Ex‐Machina

Raabe

2024

Physik in unserer Zeit

View full text Add to dashboard Cite

ZusammenfassungKünstliche Intelligenz (KI) kann zur Entwicklung von Materialien unter Einbeziehung ihrer Herstellung, Verarbeitung, inneren Strukturdefekte und chemischen Komplexität eingesetzt werden. Heute muss sie aber meist noch mit spärlichen Trainingsdaten zurechtkommen. Hybrid‐Methoden können diese Datenbasis in Verbindung mit aktiv geleiteten Experimenten verbessern. Sie schließen thermodynamische und kinetische Datenbanken, kombinatorische Hochdurchsatzexperimente, Ab‐initio‐Daten und automatisierte Sprachverarbeitung ein. Solche KI‐Methoden für das Materialdesign können auch mit physikalischen Modellen kombiniert werden. Bei allen Ansätzen ist die Identifizierung geeigneter Deskriptoren wichtig, die das gesuchte Material zu finden helfen. Aktuell ist die Verbesserung der Kausalitätsermittlung bei der Materialentwicklung mittels KI ein wichtiges Forschungsfeld. Dies gilt für die effizientere Entdeckung potenziell verheißungsvoller Datenausreißer sowie die Vorhersage außerhalb der Trainingsbereiche der KI.

show abstract

Accelerating the design of compositionally complex materials via physics-informed artificial intelligence

Cited by 34 publications

References 165 publications

Perspectives on Corrosion Studies Using Scanning Electrochemical Cell Microscopy: Challenges and Opportunities

Perspectives on Corrosion Studies Using Scanning Electrochemical Cell Microscopy: Challenges and Opportunities

Physics-informed machine learning and its structural integrity applications: state of the art

Metalle Ex‐Machina

Contact Info

Product

Resources

About